公开(公告)号：US20140196003A1

公开(公告)日：2014-07-10

申请号：US14232046

申请日：2011-08-03

申请人： Shigetoshi Sakimura ,  Masanori Miyoshi

发明人： Shigetoshi Sakimura ,  Masanori Miyoshi

IPC分类号： G06F9/44

CPC分类号： G06F8/20 ,  G06F8/35

摘要： The present invention includes four types of component diagrams, namely, an input/output data memory management component diagram, an input data value setup component diagram, a library execution component diagram, and an output data value acquisition component diagram, with respect to image processing library functions for a programming language and to an input/output data structure for the image processing library functions. The present invention also includes upper-level component diagrams, which are prepared by connecting the four types of component diagrams as lower-level component diagrams in the order of use, writes an algorithm by combining the lower- and upper-level component diagrams, and executes the written algorithm. From the written algorithm, the present invention generates a programming language source code for calling an image processing library.

摘要翻译： 本发明包括关于图像处理的四种类型的组件图，即输入/输出数据存储器管理组件图，输入数据值设置组件图，库执行组件图和输出数据值获取组件图 用于编程语言的库函数以及图像处理库函数的输入/输出数据结构。 本发明还包括上级组件图，其通过将四种类型的组件图按照使用顺序连接成下级组件图来编写，通过组合下级和上级组件图来写入算法，以及 执行书面算法。 根据本发明的编写算法，生成用于调用图像处理库的编程语言源代码。

公开(公告)号：US08294765B2

公开(公告)日：2012-10-23

申请号：US12714655

申请日：2010-03-01

申请人： Masaya Itoh ,  Masanori Miyoshi ,  Masato Kazui ,  Hiromasa Fujii ,  Shun'ichi Kaneko ,  Hidenori Takauji

发明人： Masaya Itoh ,  Masanori Miyoshi ,  Masato Kazui ,  Hiromasa Fujii ,  Shun'ichi Kaneko ,  Hidenori Takauji

IPC分类号： H04N7/18

CPC分类号： G08B13/19604 ,  G06K9/00771 ,  G06K2009/3291 ,  G06T7/254 ,  G06T2207/10016 ,  G06T2207/30196

摘要： This is a video image monitoring system which can effectively detect a mobile object appearing in a captured video image even if a background image and other camera condition change continuously. The video image monitoring system comprises: a video-image-capturing section 100 for putting out image data based on a video image signal obtained by using a camera 10; a mobile-object-candidate-area-detecting section 101 for extracting a candidate area of a mobile object from the image data; and a mobile-object-detecting section 102 for determining whether the candidate area is the mobile object. The mobile-object-candidate-area-detecting section 101 quantizes a brightness gradient direction of the image data, and calculates a spatio-temporal histogram which represents the frequency of a direction code appearing in a predetermined spatio-temporal space. After that, the mobile-object-candidate-area-detecting section 101 calculates a statistical spatio-temporal space evaluation value of the spatio-temporal histogram. The mobile-object-detecting section 102 uses the spatio-temporal space richness to determine whether the candidate area is the mobile object.

摘要翻译： 这是即使背景图像和其他照相机条件不断变化，也可以有效地检测出现在拍摄的视频图像中的移动物体的视频图像监视系统。 视频图像监视系统包括：基于通过使用照相机10获得的视频图像信号来输出图像数据的视频图像捕获部分100; 移动对象候选区域检测部分101，用于从图像数据中提取移动对象的候选区域; 以及用于确定候选区域是移动对象的移动对象检测部分102。 移动对象候选区域检测部101对图像数据的亮度梯度方向进行量化，并且计算表示出现在预定空间 - 时间空间中的方向代码的频率的时空直方图。 之后，移动对象候选区域检测部101计算时空直方图的统计时空空间评价值。 移动对象检测部102使用空间 - 时间空间丰富度来确定候选区域是否是移动对象。

公开(公告)号：US20120076356A1

公开(公告)日：2012-03-29

申请号：US13213202

申请日：2011-08-19

申请人： Yuan LI ,  Masanori Miyoshi ,  Masaya Itoh ,  Ryou Yumiba

发明人： Yuan LI ,  Masanori Miyoshi ,  Masaya Itoh ,  Ryou Yumiba

IPC分类号： G06K9/00

CPC分类号： G08B13/19602

摘要： Behavior authority may be changed depending on a behavior performed by a person. Therefore, it is necessary to change the judgment criteria whether the behavior is anomalous or normal, in association with the changed behavior authority. Herein, an anomaly detection apparatus is provided, which calculates the behavior authority information of which judgment criteria of the anomalous and normal behaviors are changed corresponding to the behavior performed by the person, detects whether the behavior shown by the person is anomalous or not, and issues an alarm when the anomalous behavior is detected.

摘要翻译： 行为权限可以根据个人执行的行为而改变。 因此，与改变的行为权力相关联，有必要改变判断标准是否是异常或正常的。 这里，提供了一种异常检测装置，其根据由人执行的行为来计算异常和正常行为的判断标准被改变的行为权威信息，检测该人显示的行为是否是异常的，以及 发现异常行为时发出警报。

公开(公告)号：US20050041489A1

公开(公告)日：2005-02-24

申请号：US10947275

申请日：2004-09-23

申请人： Yasuhiro Nakatsuka ,  Shigeru Matsuo ,  Jun Satoh ,  Masanori Miyoshi ,  Koyo Katsura ,  Takashi Sone

发明人： Yasuhiro Nakatsuka ,  Shigeru Matsuo ,  Jun Satoh ,  Masanori Miyoshi ,  Koyo Katsura ,  Takashi Sone

IPC分类号： G06T15/50 ,  G06T15/80 ,  G11C7/00

CPC分类号： G06T1/60 ,  G06T11/40 ,  G06T15/50 ,  G06T15/80

摘要： In a data processor and a shading apparatus used in the data processor, the data processor selects an address based on the information of a memory or a translation look-aside buffer. Therefore, even when the same data are accessed, a different address at high speed is adopted according to the hardware, object to be processed, processing, etc. A plurality of geometric vectors are given as the parameters for the vertexes of a picture, the vectors are interpolated in the picture, and the luminance of each small area in the figure is calculated using the vectors generated by the interpolation. Therefore, a spotlight or highlight can be expressed with high accuracy and at high speed even when the amount of the hardware and the extent of the picture are small.

摘要翻译： 在数据处理器中使用的数据处理器和着色装置中，数据处理器根据存储器或翻译后备缓冲器的信息来选择一个地址。 因此，即使在访问相同的数据的情况下，也可以根据硬件，被处理对象，处理等来采用高速的不同的地址。作为图像的顶点的参数，给出多个几何矢量， 矢量被内插在图像中，并且使用通过内插生成的矢量来计算图中每个小区域的亮度。 因此，即使当硬件的数量和图像的程度小时，也可以高精度和高速度地表现聚光灯或高光。